Unlimited OCR vs Chunkr
Pick Unlimited OCR to turn long reports and books into Markdown or text with bounding boxes in one pass, under an MIT licence. Pick Chunkr to parse PDFs, slides, Word files and images into semantic chunks for RAG, with a hosted API or a self-hosted Docker setup. The main split is scope: Unlimited OCR reads 40+ page documents in one forward pass, while Chunkr handles more input formats and returns HTML and JSON.
Unlimited OCRbaidu/unlimited-ocr | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 1.2 s / page | 3.0 s / page |
| Best for | Books and very long documents | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 30+ languages | Multilingual |
| Max pages per request | 1,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose Unlimited OCR if
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in as one request.
- The MIT licence allows commercial use with no copyleft, so you can ship it in a closed product.
- Baidu reports 77.1 on MarathonDocBench for Unlimited OCR 2, against 33.7 for the next model.
Choose Chunkr if
- It accepts PDF, PPT, Word and images, and returns HTML, Markdown, JSON and bounding boxes.
- It does semantic chunking, which suits RAG over PDFs and slides.
- Self-hosting runs through Docker with GPU, CPU-only and Mac ARM options, and works with any OpenAI-compatible LLM endpoint.
Key differences
| Unlimited OCR | Chunkr | |
|---|---|---|
| Licence | MIT, commercial use allowed, no copyleft | AGPL-3.0, or a commercial licence for closed use |
| How you run it | Self-host with vLLM, SGLang or transformers; hosted endpoint in Baidu Cloud's OCR product | Cloud API, or open-source self-host via Docker that needs an external LLM endpoint |
| Price | Free self-hosted, you pay for compute; hosted pricing not published | Hosted credit-based plans, official prices not verified; open-source version is free, you pay for compute and an LLM endpoint |
| Output formats | Markdown, plain text, bounding boxes | HTML, Markdown, JSON, bounding boxes |
| Hardware | NVIDIA GPU with CUDA 12.9 or 13.0; version 2 under SGLang runs out of memory on 12 GB GPUs; no CPU-only use | GPU, CPU-only and Mac ARM options |
| Benchmarks | ParseBench mean 46.17 (independent); MPDocBench 84.6 and MarathonDocBench 77.1 for version 2 (by the authors) | Not published |
| Known failure | Text repetition and looping, hallucinated text, bbox coordinate loops under SGLang on GB10 GPUs, and bold or italic styling mostly lost | Open-source version uses community models that are less accurate than the cloud's, and Excel is not supported there |
Sources
- Hugging Face model card
- MarkTechPost on Unlimited OCR 2
- Issue #116 OOM on 12 GB
- Chunkr GitHub README
- Chunkr site
What each one is
Unlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "baidu/unlimited-ocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesChunkr alternativesBest OCR models in 2026